Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
24 lines
786 B
Python
24 lines
786 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
from vllm.model_executor.layers.quantization import get_quantization_config
|
|
from vllm.platforms import current_platform
|
|
|
|
|
|
def is_quant_method_supported(quant_method: str) -> bool:
|
|
# Currently, all quantization methods require Nvidia or AMD GPUs
|
|
if not (current_platform.is_cuda() or current_platform.is_rocm()):
|
|
return False
|
|
|
|
try:
|
|
current_platform.verify_quantization(quant_method)
|
|
except ValueError:
|
|
return False
|
|
|
|
capability = current_platform.get_device_capability()
|
|
assert capability is not None
|
|
|
|
min_capability = get_quantization_config(quant_method).get_min_capability()
|
|
|
|
return capability.to_int() >= min_capability
|